performing-dmarc-policy-enforcement-rollout

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's runtime scripts (scripts/agent.py and scripts/process.py) perform live DNS lookups of public TXT records (e.g., _dmarc., domain TXT, ._domainkey.) and parse those untrusted, publicly authored records to produce findings and drive decisions (scores, next actions, rollout changes) as described in SKILL.md and the API reference, which meets the criteria for ingesting and acting on third-party content.